Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userValNorm Quantifies Semantics to Reveal Consistent Valence Biases Across Languages and Over Centuries
Valnorm يحدد دلالات للكشف عن تحيزات التكافؤ متسقة عبر اللغات وعدد القرون
109
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعلم Word Ageddings تحيزات ضمنية من العظميات اللغوية التي تم التقاطها إحصائيات Word في حدوثها. من خلال تمديد الطرق التي تقيس تحيزات تشبه الإنسان في Word Embeddings، نقدم Valnorm، وهي مهمة وطريقة تقييم جوهرية جديدة لتحديد البعد الافتراضي للتأثير في مجموعات الكلمة المصنوعة من البشرية من علم النفس الاجتماعي. نحن نطبق Valnorm على Adgeddings كلمة ثابتة من سبع لغات (الصينية والإنجليزية والألمانية والبولندية والبرتغالية والإسبانية والتركية) من النص الإنجليزي التاريخي الممتد إلى 200 عام. يحقق Valnorm دقة عالية باستمرار في تحديد تكاليف مجموعات كلمات المجموعة غير التمييزية وغير الاجتماعية. على وجه التحديد، يحقق Valnorm ترابط بيرسون ل R = 0.88 لعشرات الحكم البشري من التكافؤ لمدة 399 كلمة تم جمعها لإنشاء معايير ممتعة باللغة الإنجليزية. على النقيض من ذلك، نقيس القوالب النمطية الجنسانية باستخدام نفس مجموعة من embeddings Word وتجد أن التحيزات الاجتماعية تختلف عبر اللغات. تشير نتائجنا إلى أن جمعيات التكافؤ في كلمات الفريق غير التمييزية غير التمييزية تمثل جمعيات مشتركة على نطاق واسع، بسب سبع لغات وأكثر من 200 عام.
Word embeddings learn implicit biases from linguistic regularities captured by word co-occurrence statistics. By extending methods that quantify human-like biases in word embeddings, we introduce ValNorm, a novel intrinsic evaluation task and method to quantify the valence dimension of affect in human-rated word sets from social psychology. We apply ValNorm on static word embeddings from seven languages (Chinese, English, German, Polish, Portuguese, Spanish, and Turkish) and from historical English text spanning 200 years. ValNorm achieves consistently high accuracy in quantifying the valence of non-discriminatory, non-social group word sets. Specifically, ValNorm achieves a Pearson correlation of r=0.88 for human judgment scores of valence for 399 words collected to establish pleasantness norms in English. In contrast, we measure gender stereotypes using the same set of word embeddings and find that social biases vary across languages. Our results indicate that valence associations of non-discriminatory, non-social group words represent widely-shared associations, in seven languages and over 200 years.
References used
https://aclanthology.org/
rate research
Read More
How would you explain Bill Gates to a German? He is associated with founding a company in the United States, so perhaps the German founder Carl Benz could stand in for Gates in those contexts. This type of translation is called adaptation in the tran
slation community. Until now, this task has not been done computationally. Automatic adaptation could be used in natural language processing for machine translation and indirectly for generating new question answering datasets and education. We propose two automatic methods and compare them to human results for this novel NLP task. First, a structured knowledge base adapts named entities using their shared properties. Second, vector-arithmetic and orthogonal embedding mappings methods identify better candidates, but at the expense of interpretable features. We evaluate our methods through a new dataset of human adaptations.
State-of-the-art multilingual systems rely on shared vocabularies that sufficiently cover all considered languages. To this end, a simple and frequently used approach makes use of subword vocabularies constructed jointly over several languages. We hy
pothesize that such vocabularies are suboptimal due to false positives (identical subwords with different meanings across languages) and false negatives (different subwords with similar meanings). To address these issues, we propose Subword Mapping and Anchoring across Languages (SMALA), a method to construct bilingual subword vocabularies. SMALA extracts subword alignments using an unsupervised state-of-the-art mapping technique and uses them to create cross-lingual anchors based on subword similarities. We demonstrate the benefits of SMALA for cross-lingual natural language inference (XNLI), where it improves zero-shot transfer to an unseen language without task-specific data, but only by sharing subword embeddings. Moreover, in neural machine translation, we show that joint subword vocabularies obtained with SMALA lead to higher BLEU scores on sentences that contain many false positives and false negatives.
Neural Machine Translation (NMT) models have been observed to produce poor translations when there are few/no parallel sentences to train the models. In the absence of parallel data, several approaches have turned to the use of images to learn transl
ations. Since images of words, e.g., horse may be unchanged across languages, translations can be identified via images associated with words in different languages that have a high degree of visual similarity. However, translating via images has been shown to improve upon text-only models only marginally. To better understand when images are useful for translation, we study image translatability of words, which we define as the translatability of words via images, by measuring intra- and inter-cluster similarities of image representations of words that are translations of each other. We find that images of words are not always invariant across languages, and that language pairs with shared culture, meaning having either a common language family, ethnicity or religion, have improved image translatability (i.e., have more similar images for similar words) compared to its converse, regardless of their geographic proximity. In addition, in line with previous works that show images help more in translating concrete words, we found that concrete words have improved image translatability compared to abstract ones.
While emotions are universal aspects of human psychology, they are expressed differently across different languages and cultures. We introduce a new data set of over 530k anonymized public Facebook posts across 18 languages, labeled with five differe
nt emotions. Using multilingual BERT embeddings, we show that emotions can be reliably inferred both within and across languages. Zero-shot learning produces promising results for low-resource languages. Following established theories of basic emotions, we provide a detailed analysis of the possibilities and limits of cross-lingual emotion classification. We find that structural and typological similarity between languages facilitates cross-lingual learning, as well as linguistic diversity of training data. Our results suggest that there are commonalities underlying the expression of emotion in different languages. We publicly release the anonymized data for future research.
Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is genera
lly acknowledged that parallel corpora are critical for improving the model performance, existing methods are often constrained by the size of parallel corpora, especially for low-resource languages. In this paper, we propose Ernie-M, a new training method that encourages the model to align the representation of multiple languages with monolingual corpora, to overcome the constraint that the parallel corpus size places on the model performance. Our key insight is to integrate back-translation into the pre-training process. We generate pseudo-parallel sentence pairs on a monolingual corpus to enable the learning of semantic alignments between different languages, thereby enhancing the semantic modeling of cross-lingual models. Experimental results show that Ernie-M outperforms existing cross-lingual models and delivers new state-of-the-art results in various cross-lingual downstream tasks. The codes and pre-trained models will be made publicly available.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
